Data-driven deep-learning forecasting for oil production and pressure

Werneck, Rafael de Oliveira; Prates, Raphael; Moura, Renato; Gonçalves, Maiara Moreira; Castro, Manuel; Soriano-Vargas, Aurea; Júnior, Pedro Ribeiro Mendes; Hossain, M.M.; Zampieri, Marcelo Ferreira; Ferreira, André; Davólio, Alessandra; Schiozer, Denis José; Rocha, Anderson

doi:10.1016/j.petrol.2021.109937

Cited by 34 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…where: s 2 is an estimate of the variance of d m = L(e t + m (1) ) − L(e t + m (2) ). Here, the asymptotic distribution of the DM statistic obeys N (0,1).…”

Section: Performance Comparison Of Single Forecasting Methods As Show...mentioning

confidence: 99%

“…DM Test. In the DM statistic, {x i ;i = 1, 2, •••, t + p} denotes a set of observation series, and {x i (1) ;i = 1, 2, •••, t + p} and {x i (2) ;i = 1, 2, •••, t + p} denote two sets of prediction value series obtained by two different prediction models, respectively. The prediction errors obtained from the two prediction models…”

Section: Performance Comparison Of Single Forecasting Methods As Show...mentioning

confidence: 99%

“…Maintaining a stable and efficient rate of oil production is essential for achieving this goal. Forecasting oilfield production serves as a foundation for the scientific management of oilfields and the creation of production plans . These forecasts can be utilized to regulate oilfield production operations and adjust production levels to meet the changing economic market demands.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Research on the Application of Integrated Learning Models in Oilfield Production Forecasting

Ni,

Xin,

et al. 2023

ACS Omega

View full text Add to dashboard Cite

Forecasting oil production is crucially important in oilfield management. Currently, multifeature-based modeling methods are widely used, but such modeling methods are not universally applicable due to the different actual conditions of oilfields in different places. In this paper, a time series forecasting method based on an integrated learning model is proposed, which combines the advantages of linearity and nonlinearity and is only concerned with the internal characteristics of the production curve itself, without considering other factors. The method includes processing the production history data using singular spectrum analysis, training the autoregressive integrated moving average model and Prophet, training the wavelet neural network, and forecasting oil production. The method is validated using historical production data from the J oilfield in China from 2011 to 2021, and compared with single models, Arps model, and mainstream time series forecasting models. The results show that in the early prediction, the difference in prediction error between the integrated learning model and other models is not obvious, but in the late prediction, the integrated model still predicts stably and the other models compared with it will show more obvious fluctuations. Therefore, the model in this article can make stable and accurate predictions.

show abstract

“…where: s 2 is an estimate of the variance of d m = L(e t + m (1) ) − L(e t + m (2) ). Here, the asymptotic distribution of the DM statistic obeys N (0,1).…”

Section: Performance Comparison Of Single Forecasting Methods As Show...mentioning

confidence: 99%

Section: Performance Comparison Of Single Forecasting Methods As Show...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on the Application of Integrated Learning Models in Oilfield Production Forecasting

Ni,

Xin,

et al. 2023

ACS Omega

View full text Add to dashboard Cite

show abstract

“…Lags tell us the time delay between a cause and the occurrence of its effect. Related to time series, ML algorithms have been used for classification 8 , clustering 9 , and forecasting 10,11 , but little work has been done to employ ML to infer causal relationships in time series (see Moraffah et al 12 for a full review in the subject).…”

Section: Introductionmentioning

confidence: 99%

Time series causal relationships discovery through feature importance and ensemble models

Castro

Júnior

Soriano-Vargas

et al. 2023

Preprint

View full text Add to dashboard Cite

Inferring causal relationships from observational data is a key challenge when seeking to understand the interpretability of Machine Learning models. Given the ever increasing amount of observational data available in many areas, Machine Learning algorithms used for forecasting have increased their complexity, leading to a less understandable path of how a decision is made by the model. With this in mind, we propose leveraging ensemble models, e.g., Random Forest, to assess which input features the trained model pays more attention to when making a forecast and, in this way, establish causal relationships between the variables. The advantage of those algorithms is the possibility of obtaining the feature importance, which allows us to build the causal network. We apply our methods to estimate causality in time series for two domains: One climate dataset and two oil field production datasets. We aim to perform causal discovery, i.e., establish the existing connections between the variables in each dataset. Through an iterative process of improving the forecasting of a target’s value, we evaluate whether the forecasting improves by adding information from a new potential driver; if so, we state that the driver causally affects the target. On the oil field related datasets, the results we obtained based on causal analysis agree with the interwell connections already confirmed by tracer information; for the cases when the tracer data are available, we used it as our ground truth. This agreement between both estimated and confirmed connections provides us the confidence about the effectiveness of our proposed methodology. To our knowledge this is the first time causal analysis using solely production data is employed to discover interwell connections in an oil field related dataset.

show abstract

“…El pronóstico de series de tiempo es una tarea muy utilizada en los diversos campos como negocios [4]; energía [5]; medio ambiente [6]; precio de acciones [7]; ciencias de la computación [8]; ingeniería [9] y epidemia [10]. Su objetivo es determinar el resultado más probable de una variable, con el propósito de tomar buenas decisiones en la planificación y control orientadas a los requerimientos del mercado [11].…”

Section: Introductionunclassified

Copper Monthly Price Forecast with Time Series Models

Cotrina-Teatino¹,

Araujo²,

Vidal³

et al. 2022

Proceedings of the 2nd LACCEI International Multiconference on Entrepreneurship, Innovation and Regional Development (LEIRD 202

View full text Add to dashboard Cite

The research design was quantitative with a predictive scope, real information on monthly copper prices since September 2020 was used to August 2022. The models used as time series forecasting methods were moving average forecasting, weighted moving average, simple exponential smoothing, Holt exponential smoothing, and Winters exponential smoothing. The adjustment of the methods to the original model used the coefficient of determination (R2) and the mean absolute percentage error (MAPE) as a measure of precision. The result indicated that the best method is simple exponential smoothing, where the forecast copper price for September 2022 was $3.60/lb, the mean absolute percentage error (MAPE) was 4.4% and the coefficient of determination (R2) was 0.86. Finally, it is concluded that with the time series forecasting methods it is possible to forecast the price of copper.

show abstract

Data-driven deep-learning forecasting for oil production and pressure

Cited by 34 publications

References 27 publications

Research on the Application of Integrated Learning Models in Oilfield Production Forecasting

Research on the Application of Integrated Learning Models in Oilfield Production Forecasting

Time series causal relationships discovery through feature importance and ensemble models

Copper Monthly Price Forecast with Time Series Models

Contact Info

Product

Resources

About